Extend monitoring and update portfolio

Add hostmetrics receiver and OTel Collector telemetry, and move
Alertmanager and Blackbox scraping to the collector. Raise collector
memory limits, restrict Blackbox to HTTP 200, and add collector and
Caddy down alerts with inhibition. Update portfolio title and copy.
This commit is contained in:
2026-08-05 19:49:18 +00:00
parent d38b941e0e
commit ede28f6d12
8 changed files with 82 additions and 31 deletions
+16
View File
@@ -9,3 +9,19 @@ groups:
annotations:
summary: "{{ $labels.instance }} est down"
description: "Le service {{ $labels.instance }} ne répond plus depuis plus d'1 minute."
- alert: OtelCollectorDown
expr: up{job="otel-collector"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "OTel Collector est down"
description: "L'OTel Collector ne répond plus depuis plus d'1 minute."
- alert: CaddyDown
expr: up{job="reverse_caddy"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "Caddy est down"
description: "Le reverse proxy Caddy ne répond plus depuis plus d'1 minute."
+6
View File
@@ -4,6 +4,12 @@ route:
repeat_interval: 8760h
group_wait: 10s
inhibit_rules:
- source_matchers:
- alertname = "CaddyDown"
target_matchers:
- alertname = "ServiceDown"
receivers:
- name: ntfy
webhook_configs:
+2 -18
View File
@@ -11,23 +11,7 @@ alerting:
- alertmanager:9093
scrape_configs:
- job_name: alertmanager
- job_name: otel-collector
static_configs:
- targets:
- alertmanager:9093
- job_name: blackbox_http
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- https://www.qpismont.fr
- https://gitea.qpismont.fr
- https://woodpecker.qpismont.fr
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox_exporter:9115
- otel-collector:8888